← All skills
hugging-face-model-trainer
75 / 100 · Review before installing
Check before installing. Some of what it can do is expected: a devops skill usually runs commands, installs tools and uses cloud credentials.
By iradoweck/antigravity-awesome-skills (GitHub) · devops · 30 stars · scanned at commit 2984de1
Train or fine-tune language and vision models using TRL (Transformer Reinforcement Learning) or Unsloth with Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment.
Works with any agent that supports SKILL.md skills.
What this skill can do
Downloads and installs other software
The author does not mention this. Expected for a devops skill.
Found in 12 places.
Show 9 more
Runs commands on your computer
The author does not mention this. Expected for a devops skill.
Found in 20 places.
Show 17 more
- skills/hugging-face-model-trainer/references/gguf_conversion.md, line 50
subprocess.run([ - skills/hugging-face-model-trainer/references/reliability_principles.md, line 100
subprocess.run(["make", "-C", "/tmp/llama.cpp", "llama-quantize"], check=True) - skills/hugging-face-model-trainer/references/reliability_principles.md, line 103
subprocess.run([ - skills/hugging-face-model-trainer/references/reliability_principles.md, line 108
subprocess.run([ - skills/hugging-face-model-trainer/references/reliability_principles.md, line 183
subprocess.run(["git", "clone", "https://github.com/ggerganov/llama.cpp.git", "/tmp/llama.cpp"]) - skills/hugging-face-model-trainer/references/reliability_principles.md, line 184
subprocess.run(["make", "-C", "/tmp/llama.cpp", "llama-quantize"]) # FAILS: no gcc/make - skills/hugging-face-model-trainer/references/reliability_principles.md, line 187
subprocess.run(["apt-get", "update", "-qq"], check=True) - skills/hugging-face-model-trainer/references/reliability_principles.md, line 188
subprocess.run(["apt-get", "install", "-y", "-qq", "build-essential", "cmake"], check=True) - skills/hugging-face-model-trainer/references/reliability_principles.md, line 189
subprocess.run(["git", "clone", "https://github.com/ggerganov/llama.cpp.git", "/tmp/llama.cpp"]) - skills/hugging-face-model-trainer/references/reliability_principles.md, line 228
subprocess.run([...], check=True, capture_output=True) - skills/hugging-face-model-trainer/references/reliability_principles.md, line 232
result = subprocess.run( - skills/hugging-face-model-trainer/references/reliability_principles.md, line 241
except subprocess.CalledProcessError as e: - skills/hugging-face-model-trainer/scripts/convert_to_gguf.py, line 58
if subprocess.run(["which", "git"], capture_output=True).returncode != 0: - skills/hugging-face-model-trainer/scripts/convert_to_gguf.py, line 66
has_make = subprocess.run(["which", "make"], capture_output=True).returncode == 0 - skills/hugging-face-model-trainer/scripts/convert_to_gguf.py, line 67
has_cmake = subprocess.run(["which", "cmake"], capture_output=True).returncode == 0 - skills/hugging-face-model-trainer/scripts/convert_to_gguf.py, line 84
result = subprocess.run( - skills/hugging-face-model-trainer/scripts/convert_to_gguf.py, line 94
except subprocess.CalledProcessError as e:
Connects to the internet
The author does not mention this. Expected for a devops skill.
Found in 6 places.
Show 3 more
Safer alternatives
Low-risk skills in the same category (devops) that look related. Check that one does what you need.
Other copies in this repository
iradoweck/antigravity-awesome-skills has 2 more folders with a skill named hugging-face-model-trainer. This page shows the lowest-scoring copy.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'hugging-face-model-trainer' ] || [ -L ~/.agents/skills/'hugging-face-model-trainer' ]; then echo 'A skill folder named hugging-face-model-trainer already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/iradoweck/antigravity-awesome-skills' "$d" && git -C "$d" checkout --quiet '2984de11956e413008c6f98121cd141c499e47a3' -- 'skills/hugging-face-model-trainer' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/hugging-face-model-trainer' ~/.agents/skills/'hugging-face-model-trainer' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'hugging-face-model-trainer' ~/.claude/skills/'hugging-face-model-trainer' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
The badge for iradoweck/antigravity-awesome-skills shows the score of its lowest-scoring skill.
[](https://zalavijaysinh.github.io/skilltrust/repos/iradoweck/antigravity-awesome-skills/)
Score history
| Date | Version | Score |
|---|
| 2026-11-08 | 2984de1 | 75 |
| 2026-11-06 | 2984de1 | 65 |